Global ray-casting range image registration
- Linh Tao^{1}Email author,
- Tam Bui^{2} and
- Hiroshi Hasegawa^{3}
DOI: 10.1186/s41074-017-0025-4
© The Author(s) 2017
Received: 29 March 2016
Accepted: 12 April 2017
Published: 8 May 2017
Abstract
This paper presents a novel method for pair-wise range image registration, a backbone task in world modeling, parts inspection and manufacture, object recognition, pose estimation, robotic navigation, and reverse engineering. The method finds the most suitable homogeneous transformation matrix between two constructed range images to create a more complete 3D view of a scene. The proposed solution integrates a ray casting-based fitness estimation with a global optimization method called improved self-adaptive differential evolution. This method eliminates the fine registration steps of the well-known iterative closest point (ICP) algorithm used in previously proposed methods, and thus, is the first direct global registration algorithm. With its parallel implementation potential, the ray casting-based algorithm speeds up the fitness calculation for the global optimization method, which effectively exploits the search space to find the best transformation solution. The integration was successfully implemented in a parallel paradigm on a multi-core computer processor to solve a simultaneous 3D localization problem. The fast, accurate, and robust results show that the proposed algorithm significantly improves on the registration problem over state-of-the-art algorithms.
Keywords
Range image registration Direct global registration Adaptive differential evolution Global optimization Ray-casting 3D localization1 Introduction
The introduction of commercial depth sensing devices, such as the Microsoft Kinect and Asus Xtion, has shifted the research areas of robotics and computer vision from 2D-based imaging and laser scanning toward 3D-based depth scenes for environment processing. As physical objects or scenarios are built using more than a single image, images from different times and positions need to be aligned with each other to provide a more complete view. We call the alignment process registration, and it plays a key role in object reconstruction, scene mapping, and robot localization applications. Depending on the number of views that are processed simultaneously, registration is divided into multi-view [1] and pair-wise cases [2]. Our paper focuses on the latter case for constructed range images captured by 3D cameras. From two images, called the model and the data, the registration algorithm finds the best homogeneous transformation that aligns the data and the model image in a common coordinate system.
The iterative closest point (ICP) algorithm [3] and its variants, such as EM-ICP [4] and generalized ICP [5], have been indispensable tools in registration algorithms. ICP’s concept and implementation are easy to understand. It derives a transformation that draws images closer to each other using their L _{2} error iteratively. ICP-class algorithms have a drawback for general registration in that they require a further assumption of near-optimal initial pose transformation; otherwise, the registration process is likely to converge to local instead of global or near global optima. Some mesh and point cloud editor software programs, such as Meshlab [6], include an ICP built-in registration tool; however, they require that users perform manual pre-alignment before ICP can be applied.
To overcome the shortage of ICP-class methods, automatic registration algorithms in general perform two steps: coarse initialization and fine transformation. If two point clouds are sufficiently close, the first step can be omitted. Otherwise, researchers are faced with a big challenge. Two approaches for coarse transformation, pre-alignment estimation, or initialization exist: local and global. The former uses local descriptors (or signatures), such as PFH [7] and SIFT [8], which encode local shape variation in neighborhood points. If the key points of these descriptors appear in both registered point clouds, the initialization movement can be estimated by using sample consensus algorithms, such as RANSAC [9]. Unfortunately, it is not always guaranteed that these signatures will appear in both registered point clouds. On the other hand, global approaches, such as Go-ICP [10] and SAICP [11], take all the points into account. The computation cost is the biggest problem in this approach. In big number data cases, the computation cost becomes large. By virtue of new search algorithms, in particular heuristic optimal methods, and the increase in computer speed achieved by using multi-core computer processor units (CPUs) and graphic computation units (GPUs) [12], it is possible to find reasonable solutions using global approaches for the registration problem. When the coarse transformation has been estimated, the ICP algorithm is an efficient tool for finding the fine transformation.
By integrating optimal search tools with an ICP algorithm, researchers have created hybrid algorithms that integrate global optimizers with ICP. However, this approach has its limitations. SAICP, a parameter-based algorithm, uses simulated annealing (SA) [13] as a search engine to find the best movement combination of rotation angles and translation. However, SA is not sufficiently effective to allow its application to a complicated fitness function, where the potential of a failed convergence is high. Go-ICP converges slowly, since it uses the branch-and-bound (BnB) method, a time consuming and non-heuristic method, as a search algorithm to ensure a 100% convergence rate. In addition, ICP algorithms frequently include a kd-tree structure for searching corresponding points. Using the kd-tree nearest neighbor search method also leads to a high computation cost and a long runtime.
- -
It eliminates the ICP algorithm from the registration process and thus becomes a direct method.
- -
As other global registration methods, the new method requires no local descriptors and operates directly on raw scanning data.
- -
The method uses the improved self-adaptive differential evolution (ISADE) algorithm [14] as a search engine to find the global minima as a direct method that does not use a fine registration procedure such as ICP.
- -
Furthermore, ray casting-based error calculation reduces the computation cost and runtime because of the potential for using parallelized computation. CPU-based parallel computing procedures allow the algorithm to find the solution at a rate equivalent to the online rate.
- -
Section 1 comprises the introduction.
- -
In Section 2, the classic and up-to-date methods of range image registration are presented.
- -
In Section 3, the methodology and the new approach of the proposed method are provided.
- -
In Section 4, the experiments and results are described.
- -
In Section 5, the discussion and conclusions are presented.
2 Range image registration
This part summarises some approaches for global range image registration problem up to date.
2.1 Registration error function and ICP approach
where X={x _{ i }},{i=1,2,3,…,m} is the model point cloud and Y={y _{ j }},{j=1,2,3,…,n} is the data point cloud, x _{ i } and y _{ j }∈R ^{3} are the coordinates of the points in the point clouds, R and t are the rotation and translation matrix, respectively, \(\mathbf {y}_{\mathbf {j}^{*}}\) is the corresponding point of x _{ i } denoting the closest point in data point cloud Y. R and t are determined by Roll-Pitch-Yaw movement of three rotation angles (α,β,γ) and translation values (x,y,z).
- 1.
Compute the closest model points for each data point as in Eq. 2.
- 2.
Compute the transformation R and t based on the error obtained using Eq. 1.
- 3.
Apply R and t to the data point clouds.
- 4.
Repeat steps 1, 2, and 3 until the error obtained using (1) is smaller than a set tolerance level or the procedure reaches its maximum iteration.
Step by step, the data point cloud becomes closer to the model point cloud and the process stops at local minima. ICP’s variants, such as LMICP [16] and SICP [17], use different methods to calculate the transformation from error E(R,t). A well-known accumulation registration method in the KinectFusion algorithm [18] uses ICP to register two consecutive frames. The transformation matrix for the current frame is estimated by multiplying the matrices from the previous registration steps.
2.2 Global hybrid registration algorithm
The integration is effective in the case of point cloud data where the point number is small. For cases where the point number is large, the hybrid approach with ICP becomes slow. This method cannot therefore be implemented in real-time applications.
3 The new direct global approach
With the newly developed global search algorithms, flattening using ICP inner loops in registration becomes redundant. Our method integrates a new global search algorithm, ISADE, which is suitable for complicated fitness functions when the flattening process is not performed, and a ray casting-based corresponding search method to accelerate the objective function calculation in the registration procedure.
3.1 Ray-casting for fast corresponding point determination on constructed range image
The KinectFusion algorithm, a real-time scene reconstructing pipeline, uses ICP as the only method for registering two continuous frames. The procedure requires a powerful GPU to speed up calculations and reduce runtime. However, global registration algorithms calculate a thousand times more error functions than ICP and thus, so that these algorithms can be applied online or using less powerful processors, faster error calculation methods must be included.
Ray casting [20] is one of the most basic of the many computer graphics rendering methods. The idea behind the ray-casting method is to direct a ray from the eye through each pixel and find the closest object blocking the path of the ray. Using the material properties and light effect in the scene, rendering methods can determine the shading of the object. Some hidden surface removal algorithms use ray casting to find the closest surfaces to the eye and eliminate all others that are at a greater distance along the same ray. The Point Cloud Library [21] uses ray casting as a filtering method; it removes all points that are obscured by other points.
where z _{ i,j } is the depth of the image at pixel column i and row j.
where f x,f y,c x, and cy are the intrinsic parameters of the depth camera.
where R and t are the rotation and translation matrix, respectively, \(z^{X}_{i,j}\) is the depth of the model point cloud, and \(z^{Y(R,t)}_{i,j}\) is the depth of the data point cloud after applying the rotation and translation matrix with i,j from the ray casting process.
The ray-casting method is simple and fast (with a complexity of O(1)) and, more importantly, potentially parallel computing can be applied.
3.2 Objective function
where R and t are the rotation and translation matrix, respectively, m and n are the height and width of the image frame, and k is the inlier point number.
where N is the number of points in the data point cloud.
The ray-casting-based method makes the algorithm run significantly faster than the kd-tree-based approach. However, since a global search algorithm handles a large number of points at a huge computation cost, we take parallel implementation into consideration. Since in most computers a multi-core processor is available, using the CPU for parallel computing is convenient in most applications. In addition, CPU multi-core parallel implementation is even easier with OpenMP library [22]. Furthermore, the ray-casting process adapts well to parallel computing, and the corresponding points can be calculated in different processes or threads.
3.3 ISADE, an efficient improved version of differential evolution algorithm
3.3.1 Differential evolution
where rand_{ j }(0,1) a random number ∈[0,1].
where r _{1},r _{2},r _{3},r _{4}, and r _{5} are randomly selected integers in the range [1,N P].
where i=1,…,N P, j=1,…,D, j _{rand} is a randomly chosen integer in [1,D],rand_{ j }(0,1) is a uniformly distributed random number between 0 and 1 generated for each j and C _{ r }∈[0,1] is called the crossover control parameter. Using j _{rand} ensures the difference between the trial vector \(U_{i}^{G}\) and target vector \(X_{i}^{G}\).
where \(i = 1,\ldots, NP, X_{i}^{G+1}\) is a target vector in the next generation’s population.
3.3.2 Improvement of self-adapting control parameters in differential evolution
where r _{1},r _{2},r _{3},r _{4}, and r _{5} are randomly selected integers in the range [1,N P], where NP is the population size.
where n _{max} and n _{min} are typically chosen in the range [0,15]. Recommended values for n _{min} and n _{max} are 0.2 and 6.0 respectively.
where \(C_{r_{\text {min}}}, C_{r_{\text {medium}}}\), and \(C_{r_{\text {max}}}\) denote a low value, median value, and high value of the crossover parameter, respectively. We use recommended values of \(\tau =0.1, C_{r_{\text {min}}}=0.05, C_{r_{\text {medium}}}=0.50\), and \(C_{r_{\text {max}}}=0.95\).
4 Experiment and results
- 1)
SA proposed in Luck et al.’s paper, Registration of range data using a hybrid simulated annealing and iterative closest point algorithm.
- 2)
Particle swarm optimization (PSO) proposed in Talbi et al.’s paper, Particle swarm optimization for image processing [25].
- 3)
Genetic algorithm (GA) proposed in Valsecchi et al.’s paper, An image registration approach using genetic algorithms [26].
- 4)
DE proposed in Falco et al.’s paper, Differential evolution as a viable tool for satellite image registration [27].
We also calculated the ray casting-based error of the KinectFusion and Go-ICP algorithms for further comparison. All algorithms were implemented in C++ and compiled with GNU/g++ tool.
4.1 Range image dataset
Chess dataset: image sequence 2, frame 960 vs frame 980.
Other datasets: image sequence 1, frame 000 vs frame 020.
These “PNG” format depth images are sub-sampled into a smaller resolution of 128×96, which is five times smaller than the original resolution of 640×480 in each dimension. The purpose of using a dataset with a smaller number of points is to achieve a suitable runtime while preserving robustness and accuracy.
4.2 Parameter settings
For each method, 30 runs were performed. The search space had rotation angles and translation limited at [−π/5,π/5] and [−1,1] separately. This means that the limitation of the rotation angles was 36° and of the translation was 1 m.
Algorithm configuration
Algorithm | DE | GA | SA | PSO | Go-ICP |
---|---|---|---|---|---|
Parameters | F _{0}=0.8 | P c=0.95; | α=0.995 | elites=4 | trimFraction=0.0 |
C _{ r }=0.9 | P m=0.1; | neighbors=5 | |||
DE/rand/1/bin | elites=5 | c1=c2=c3=2.1 | distTransSize=50 | ||
Maxgen | 100 | 100 | 3000 | 100; | |
Population | 30 | 30 | 30 | data subsample=1000 points |
4.3 Comparison with KinectFusion algorithm
where \(T_{i}^{j}\) is the transformation matrix to move frame j to align with frame i,T _{ i } and T _{ j } are the homogeneous transpose matrix for the camera at frame i and j, respectively, and \(R_{i}^{j}\) and \(T_{i}^{j}\) are the rotation and translation matrix of \(T_{i}^{j}\), respectively.
Error comparison between new method, KinectFusion, and Go-ICP algorithms
Chess | Fire | Heads | Office | Pumpkin | RedKitchen | Stairs | |
---|---|---|---|---|---|---|---|
Our method | 0.10230 | 0.03179 | 0.01000 | 0.03096 | 0.05563 | 0.03481 | 0.00883 |
KinectFusion | 22.37200 | 0.24311 | 2.99067 | 3.85941 | 0.11136 | 0.09836 | 0.01561 |
Go-ICP | nan | 0.825212 | 0.01832 | 0.358507 | inf | 1.5387 | 2.28615 |
In these figures, the proposed algorithm outperforms KinectFusion is clearly seen. Even in the best case of KinectFusion, such as Stairs or RedKitchen, the overlapping regions, where the two colors are mixed together, are not as clearly seen as in the results of the proposed algorithm.
4.4 Comparison with Go-ICP algorithm
From authors contributed code [29], we performed experiments to compare our method with Go-ICP on accuracy, runtime, and robustness. Go-ICP configuration parameters were set as in Table 1 with the identical searching boundary with other methods. distTransSize is the number of nodes in translation searching boundary. It was set to 50 or translation resolution is at 40 mm. Raising accuracy by increasing distTransSize to 500 or 4 mm resolution effort failed due to infinite runtime. Go-ICP were able to register Heads and Office datasets at distTransSize of 100 with runtime presented in Table 5.
The disadvantage of big resolution could be compensated by inner ICP loops; however, the smaller the resolution, the more accurate the algorithm is. We set the data subsample to 1000; Go-ICP reaches infinitive runtime at the original 128×96 resolution.
Together with KinectFusion and our method errors, Table 2 presents the mean errors of Go-ICP algorithm where “nan” stands for undefined result in the case of infinitive runtime and “inf” stands for wrong convergence with few overlapse points. Over all, only heads and office showed good convergence with small error and run time. However, those small errors are still bigger than the new method.
Figures 9 and 10 also show the registration results of Go-ICP algorithm on the right side together with new method results in the center and KinectFusion algorithm result on the left side. From those figures, the new method better performance is clearly seen. In the case of RedKitchen dataset, the wrong convergence results of Go-ICP were observed, the error was small because of small over-lapsed percentage.
Average runtime for Go-ICP on different datasets are presented in Table 5 where average run times of the new algorithm at different generation numbers are presented. In the table, “inf” values stand for infinitive runtime. Go-ICP was fast in case of heads dataset or extreme slow for the case of Chess dataset.
Over all, the new methods outperformed Go-ICP on experiment datasets in accuracy, runtime, and robustness.
4.5 Comparison between different optimization algorithms
Results of Chess, Fire, Heads, and Office datasets
Scene name | Algorithm | Min | Max | Mean | St. dev. |
---|---|---|---|---|---|
Chess | ISADE | 0.10047 | 0.11187 | 0.10230 | 0.002821482 |
KinectFusion | DE | 0.17453 | 3.92808 | 0.29860 | 0.112087291 |
ref: 22.372 | GA | 1.44923 | 1.80180 | 2.53723 | 0.691936150 |
SA | 1.11736 | 2.55157 | 1.65871 | 0.400817542 | |
PSO | 1.19899 | 2.58186 | 1.72316 | 0.459892382 | |
Fire | ISADE | 0.03169 | 0.03196 | 0.03179 | 8.70855E −005 |
KinectFusion | DE | 0.03873 | 0.26059 | 0.10263 | 0.066038287 |
ref: 0.243112 | GA | 0.22177 | 3.93133 | 1.58268 | 0.913837133 |
SA | 0.15060 | 0.88670 | 0.45855 | 0.249700426 | |
PSO | 0.11158 | 0.63419 | 0.34592 | 0.151824890 | |
Heads | ISADE | 0.00994 | 0.01016 | 0.01000 | 7.01799E −005 |
KinectFusion | DE | 0.01276 | 0.06570 | 0.02205 | 0.012768061 |
ref: 2.99067 | GA | 0.47056 | 1.70316 | 0.97758 | 0.358190303 |
SA | 0.30740 | 1.01428 | 0.65404 | 0.264058658 | |
PSO | 0.20801 | 1.88772 | 0.54401 | 0.463097716 | |
Office | ISADE | 0.03084 | 0.03115 | 0.03096 | 8.39925E −005 |
KinectFusion | DE | 0.03195 | 0.06436 | 0.04373 | 0.009462166 |
ref: 3.85941 | GA | 0.24518 | 4.05346 | 1.88819 | 0.928751342 |
SA | 0.10385 | 2.67972 | 0.84426 | 0.720046753 | |
PSO | 0.07169 | 2.08078 | 0.58507 | 0.686244921 |
Results of Pumpkin, RedKitchen and Stairs datasets
Scene name | Algorithm | Min | Max | Mean | St. dev. |
---|---|---|---|---|---|
Pumpkin | ISADE | 0.05541 | 0.05603 | 0.05563 | 0.000175987 |
KinectFusion | DE | 0.06555 | 0.16927 | 0.11105 | 0.111050113 |
ref: 0.111361 | GA | 0.45803 | 3.15529 | 1.42922 | 0.775060060 |
SA | 0.07468 | 0.90335 | 0.49504 | 0.248322702 | |
PSO | 0.11181 | 1.43345 | 0.36443 | 0.334116975 | |
RedKitchen | ISADE | 0.03423 | 0.03759 | 0.03481 | 0.000915588 |
KinectFusion | DE | 0.05879 | 0.60304 | 0.17479 | 0.149183155 |
ref: 0.0983645 | SA | 0.52141 | 5.48133 | 2.07233 | 1.339500137 |
GA | 0.12508 | 1.58015 | 0.62601 | 0.441544434 | |
PSO | 0.05515 | 2.48188 | 0.54354 | 0.671268667 | |
Stairs | ISADE | 0.00875 | 0.00898 | 0.00883 | 0.000079463 |
KinectFusion | DE | 0.00975 | 0.04665 | 0.01767 | 0.009514675 |
ref: 0.0156084 | SA | 0.21207 | 2.24988 | 1.19252 | 0.627554990 |
GA | 0.01405 | 1.08881 | 0.29528 | 0.304574563 | |
PSO | 0.04632 | 0.96723 | 0.25021 | 0.239971819 |
Average running time (in second) on different scenes of new methods and Go-ICP
New methods | New method | Go-ICP | Go-ICP | |
---|---|---|---|---|
100 generations | 150 generations | distTransSize = 50 | distTransSize = 100 | |
Chess | 0.388414 | 0.516832 | inf | inf |
Fire | 0.385928 | 0.625765 | 14.2786 | inf |
Heads | 0.335828 | 0.562451 | 0.102944 | 0.104659 |
Office | 0.378768 | 0.560734 | 0.030326 | 34.411 |
Pumpkin | 0.410615 | 0.621756 | 104.468 | inf |
RedKitchen | 0.415258 | 0.588466 | 30.3815 | inf |
Stairs | 0.409834 | 0.597050 | 188.205 | inf |
The smaller means and standard deviations for every dataset in comparison with the other methods show the accuracy and robustness of the new search engine as compared to the state-of-the-art search algorithms. In some cases, the experimental results show that the other integrations performed better than KinectFusion. The ICP accumulating error is the reason for this poor performance.
4.6 Iterations vs convergence
These results show that, if we reduce the maximum number of iterations to 70, the results remain the same. Clearly, the smaller the iteration number, the shorter is the runtime.
4.7 Results from registering in different movement patterns and frame distances
The results with no sudden value changing between two consecutive frames verify the feasibility of applying the new algorithm in registering range images of different movement patterns and frame distances.
4.8 Runtime
For the data of 128×96 resolution, average runtime for the proposed method are shown in Table 5. In the results, the average runtime for registration is around 0.6 s for 150 iterations of all scenes. Since the distance between two frames is 20, the registering equivalence rate is 33 frames per second (fps). At this rate, when we move the camera, the algorithm are able to update the scenarios.
5 Discussion
Image registration has become a very active research area. Recently, the approach of using EAs, in particular in new methods, proved their potential for tackling the image registration problem based on their robustness and accuracy for searching for global optimal solutions. When EAs are used as search tools, good initial conditions are not necessary for avoiding local minima while converging to near-global minima solutions.
We proposed a novel registration method in which a fast ray-casting-based error calculation is integrated with a powerful self-adaptive optimization algorithm. The experimental results showed that ISADE is able to find a robust and accurate transformation matrix, while the ray-casting method is fast and efficient in calculating error for global registration problems.
A more important point is that, by eliminating inner ICP loops in hybrid integrations and fine-tuning procedures applied in previously proposed methods, the newly proposed method becomes the first direct, as well as the first online potential, global registration algorithm. Its robustness and accuracy were tested and verified in real 3D scenes captured by a Microsoft Kinect camera.
Currently, the algorithm is implemented using a CPU parallel procedure. In future work, the new algorithm can be implemented on a GPU to reduce its runtime and error while retaining its accuracy and robustness. Furthermore, the method can be extended for general point clouds from different sources by using a virtual camera surface and presenting it as a constructed surface. The proposed method is also potentially suitable for super resolution range images.
Declarations
Authors’ contributions
LT took charge of the system coding, doing experiments, data analysis and writing the whole paper excluding ISADE algorithm part at Subsection 3.3. TB took charge of coding and writing for ISADE algorithm part at Subsection 3.3. HH took charge of advisor position for paper presentation, experiment design, data analysis presentation as well English revising. All authors read and approved the final manuscript.
Competing interests
The authors declare that they have no competing interests.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Authors’ Affiliations
References
- Sharp GC, Lee SW, Wehe DK (2004) Multiview registration of 3D scenes by minimizing error between coordinate frames. IEEE Trans Pattern Anal Mach Intell 26(8): 1037–1050. doi:10.1109/TPAMI.2004.49.View ArticleMATHGoogle Scholar
- Holz D, Ichim AE, Tombari F, Rusu RB, Behnke S (2015) Registration with the Point Cloud Library: a modular framework for aligning in 3-D. IEEE Robot Autom Mag 22(4): 110–124. doi:10.1109/MRA.2015.2432331.View ArticleGoogle Scholar
- Besl P, McKay ND (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2): 239–256. doi:10.1109/34.121791.View ArticleGoogle Scholar
- Granger S, Pennec X (2002) Multi-scale EM-ICP: a fast and robust approach for surface registration In: European Conference on Computer Vision, vol. 2353, 418–432.Google Scholar
- Segal A, Haehnel D, Thrun S (2009) Generalized-ICP In: Proceedings of Robotics: Science and Systems, Seattle, USA. doi:10.15607/RSS.2009.V.021.
- Meshlab. http://meshlab.sourceforge.net/. Accessed 15 Jan 2017.
- Rusu RB, Marton ZC, Blodow N, Beetz M (2008) Persistent point feature histograms for 3D point clouds In: Proceedings of the 10th International Conference on Intelligent Autonomous Systems (IAS-10), 119–128, Baden-Baden.Google Scholar
- Sehgal A, Cernea D, Makaveeva M (2010) Real-time scale invariant 3D range point cloud registration. In: Campilho A Kamel M (eds)Image Analysis and Recognition. ICIAR 2010. Lecture Notes in Computer Science.. Springer, Berlin Heidelberg. doi:10.1007/978-3-642-13772-3_23.
- Wu F, Fang X (2007) An improved RANSAC homography algorithm for feature based image mosaic In: Proceedings of the 7th WSEAS International Conference on Signal Processing, Computational Geometry & Artificial Vision, ISCGAV’07, World Scientific and Engineering Academy and Society (WSEAS), Stevens Point, 202–207, Wisconsin. http://dl.acm.org/citation.cfm?id=1364592.1364627.
- Yang J, Li H, Jia Y (2013) Go-icp: Solving 3D registration efficiently and globally optimally In: 2013 IEEE International Conference on Computer Vision, 1457–1464, Sydney. doi:10.1109/ICCV.2013.184.
- Luck J, Little C, Hoff W (2000) Registration of range data using a hybrid simulated annealing and iterative closest point algorithm In: Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065), 3739–3744, San Francisco. doi:10.1109/ROBOT.2000.845314.
- Neumann D, Lugauer F, Bauer S, Wasza J, Hornegger J (2011) Real-time RGB-d mapping and 3-D modeling on the GPU using the random ball cover data structure In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 1161–1167, Barcelona. doi:10.1109/ICCVW.2011.6130381.
- Ingber L (1993) Simulated annealing: practice versus theory. Math Comput Model 18(11): 29–57. http://dx.doi.org/10.1016/0895-7177(93)90204-C.
- Bui T, Pham H, Hasegawa H (2013) Improve self-adaptive control parameters in differential evolution for solving constrained engineering optimization problems. J Comput Sci Technol 7(1): 59–74. doi:10.1299/jcst.7.59.View ArticleGoogle Scholar
- Marden S, Guivant J (2012) Improving the performance of ICP for real-time applications using an approximate nearest neighbour search In: Proceedings of Australasian Conference on Robotics and Automation, 3–5, New Zealand.Google Scholar
- Lim Low K (2004) Linear least-squares optimization for point-toplane ICP surface registration. Tech Rep TR04-004, Department of Computer Science, University of North Carolina at Chapel Hill.Google Scholar
- Bouaziz S, Tagliasacchi A, Pauly M (2013) Sparse iterative closest point In: Proceedings of the Eleventh Eurographics/ACMSIGGRAPH Symposium on Geometry Processing, SGP ’13, Eurographics Association, 113–123.. Aire-la-Ville, Switzerland. doi:10.1111/cgf.12178.Google Scholar
- Izadi S, Kim D, Hilliges O, Molyneaux D, Newcombe R, Kohli P, Shotton J, Hodges S, Freeman D, Davison A, Fitzgibbon A (2011) Kinect-Fusion: real-time 3d reconstruction and interaction using a moving depth camera In: Proceedings of the 24th Annual ACM Symposium on User Interface Software and Technology, UIST ’11, 559–568.. ACM, New York. doi:10.1145/2047196.2047270.Google Scholar
- Chandran S (2012) Introduction to kd-trees. University of Maryland Department of Computer Science. https://www.cs.umd.edu/class/spring2002/cmsc420-0401/pbasic.pdf.
- Roth SD (1982) Ray casting for modeling solids. Comput Graph Image Process 18(2): 109–144. doi:10.1016/0146-664X(82)90169-1.View ArticleGoogle Scholar
- Point cloud library. http://pointclouds.org/. Accessed 15 Jan 2017.
- Openmp. http://openmp.org/wp/. Accessed: 15 Jan 2017.
- Storn R, Price K (1997) Differential evolution a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11(4): 341–359. doi:10.1023/A:1008202821328.View ArticleMATHGoogle Scholar
- Tooyama S, Hasegawa H (2009) Adaptive plan system with genetic algorithm using the variable neighborhood range control In: Evolutionary Computation, 2009. CEC ’09. IEEE Congress on Evolutionary Computation, CEC ’09, 846–853. doi:10.1109/CEC.2009.4983033.
- Chen YW, Mimori A, Lin C-L (2009) Hybrid particle swarm optimization for 3-d image registration In: 16th IEEE International Conference on Image Processing (ICIP), 1753–1756, Cairo. doi:10.1109/ICIP.2009.5414613.
- Seixas FL, Ochi LS, Conci A, Saade DM (2008) Image registration using genetic algorithms In: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, GECCO ’08, 1145–1146.. ACM, New York. doi:10.1145/1389095.1389320.View ArticleGoogle Scholar
- Falco ID, Cioppa AD, Maisto D, Tarantino E (2008) Differential evolution as a viable tool for satellite image registration. Appl Soft Comput 8(4): 1453–1462. Soft Computing for Dynamic Data Mining. doi:10.1016/j.asoc.2007.10.013.
- Iterative closest point implementation C++ code. http://www.cvlibs.net/software/libicp/. Accessed 15 Jan 2017.
- Go-ICP implementation C++ code. http://iitlab.bit.edu.cn/mcislab/~yangjiaolong/go-icp/. Accessed 15 Jan 2017.